An interpretable multimodal biomechanical–radiological model for predicting fixation failure in osteoporotic hip fractures: A retrospective cohort study
Aug 2026· Medicine· Vol 105, pp. e49988· 0 citations· 25 references
Medicine
TL;DR
The random forest model demonstrated strong discriminatory ability and calibration in predicting fixation failure in this single-center retrospective cohort, and shows promise for perioperative risk stratification.
Abstract
This study aimed to develop and validate a multimodal prediction model integrating biomechanical and radiological variables to predict internal fixation failure in osteoporotic hip fractures, enabling individualized risk assessment and perioperative decision-making. Patients with osteoporotic hip fractures undergoing internal fixation between March 2019 and February 2024 were retrospectively enrolled and randomly divided into a training set (n = 249) and a validation set (n = 107) at a 7:3 ratio. The primary outcome was implant-related failure within 12 months post-surgery. In the training set, univariate analysis and multivariate logistic regression were performed to screen associated factors. Using independent predictors, 3 machine learning models (random forest, support vector machine, and K-nearest neighbors) were developed and compared. The model with the best discriminative ability, assessed by the area under the receiver operating characteristic curve (AUC) with internal validation (bootstrapping), calibration curves, and decision curve analysis, was selected to construct a nomogram. No significant differences in baseline characteristics were observed between the training and validation sets (P > .05). Multivariate logistic regression identified that bone mineral density, maximum fracture end displacement, peak stress distribution of the implant, fracture reduction alignment deviation, and implant insertion depth were significantly associated with fixation failure (P < .05). The nomogram demonstrated excellent performance in both the training (AUC = 0.887, 95% confidence interval: 0.835–0.939) and validation sets (AUC = 0.869, 95% confidence interval: 0.801–0.937). Calibration curves showed good agreement between predicted and observed risks (P > .05), and decision curve analysis indicated superior clinical net benefit across a wide threshold range. Stability testing confirmed no significant multicollinearity (variance inflation factor < 2, events per variable ≥ 5). The random forest model demonstrated strong discriminatory ability and calibration in predicting fixation failure in this single-center retrospective cohort. While the model shows promise for perioperative risk stratification, external validation in multicenter prospective studies is required before clinical implementation.
This study aimed to investigate the risk factors associated with 1-year postoperative mortality in patients with lumbar compression fractures and to construct and validate a predictive nomogram model. Clinical data of patients admitted between January 2021 and December 2024 were retrospectively analyzed. Independent predictors of 1-year mortality were identified using univariate and multivariate logistic regression analyses. A nomogram was constructed based on the final model. Model discrimination was evaluated using the receiver operating characteristic curve and the area under the curve. Calibration, Bootstrap resampling, and 10-fold cross-validation were used for internal validation. A total of 378 patients were included, of whom 21 (5.56%) died within 1 year postoperatively. Five independent predictors were identified: bone mineral density ≤ −2.5, multiple segmental fractures, age > 70 years, albumin ≤ 40 g/L, and neutrophil-to-lymphocyte ratio > 4. The nomogram showed good discriminative performance, with an area under the curve of 0.826 in the training cohort and 0.813 in the validation cohort. Calibration curves demonstrated good agreement between predicted and observed outcomes. One-year postoperative mortality in lumbar compression fracture patients is influenced by multiple clinical and inflammatory factors. The proposed nomogram demonstrates good discriminative ability and may help clinicians identify high-risk patients for early intervention.
To develop and validate machine learning models and an individualized nomogram for predicting pedicle screw loosening after posterior lumbar interbody fusion in osteoporotic patients using preoperative clinical, imaging, and bone metabolism-related medication profiles, these complementary tools offer a potentially useful framework for preoperative risk stratification and personalized management of osteoporotic patients undergoing PLIF.
Xue Yu, Wen-Bo Gu, Xiang-Hai Yu et al.· Frontiers in Medicine· 0 citations
Objective To identify independent risk factors for heterotopic ossification (HO) after open reduction and internal fixation (ORIF) of distal humeral fractures, and to construct and validate a clinically applicable risk prediction model. Methods This retrospective cohort study included 826 patients with distal humeral fractures who underwent ORIF in 3 Grade A tertiary hospitals. Multi-dimensional baseline data were collected. The primary outcome was the occurrence of HO within 6 months after surgery. Potential risk factors were screened by univariate analysis and multivariate Logistic regression. The model was internally validated using Bootstrap resampling (1,000 iterations) to estimate the mean area under the receiver operating characteristic curve (AUC), and temporally validated using a cohort of 186 patients enrolled from the same tertiary hospital (temporal external validation). Receiver operating characteristic (ROC) curve, calibration curve and decision curve analysis (DCA) were used to evaluate the model’s performance. A nomogram was also constructed for visualization. Results The overall incidence of postoperative HO was 23.7%. Age ≥ 60 years, high-energy injury, comminuted fracture, extensive intraoperative soft tissue dissection, postoperative immobilization ≥ 4 weeks and postoperative infection were independent risk factors (all P < 0.001). The internal validation AUC of the model was 0.846, and the external validation AUC was 0.823. The calibration was good (Hosmer-Lemeshow test, P = 0.610). When the risk threshold was between 8 and 75%, the clinical net benefit of the model was superior to traditional strategies. The nomogram could intuitively predict the risk of HO. Conclusion This study identified the core risk factors for HO. The established prediction model can serve as a preliminary risk-stratification tool for HO. Further prospective studies and geographically distinct external validation are still needed before this model can be applied in routine clinical practice.
Qiming Liu, Yu-Hai Wang, Zilin Zhang et al.· Frontiers in Medicine· 0 citations
The nomogram developed based on conventional clinical data in this study, has undergone internal validation and demonstrated efficacy in predicting NVCF following PVP, and serves as a valuable decision-making tool for clinicians.
Yi-Qi Wu, Qing Song, Canwei Hu et al.· Frontiers in Medicine· 0 citations
Post-fracture intercostal neuralgia in osteoporotic thoracic vertebrae is multifactorial, and middle thoracic vertebra fractures, injury of the thoracolumbar fascia, decreased bone density, intravertebral vacuum fissure, and depressive state are independent risk factors.
Dongliang Xiao, Yong-Guang Xu· International Journal of Gen...· 0 citations
BACKGROUND
Secondary fragility fractures remain a major complication after hip fracture surgery in older adults, yet individualized postoperative risk stratification remains challenging. We aimed to identify factors associated with secondary fragility fracture and internally validate an interpretable machine-learning model for three year refracture risk.
METHODS
We retrospectively analyzed adults aged ≥ 65 years who underwent surgery for a first low-energy hip fracture between 2014 and 2021. Patients were followed for three years for secondary fragility fracture. Demographic, clinical, functional, and rehabilitation variables were extracted from electronic medical records. Cox regression with multiple imputation was performed to evaluate time-to-event associations. XGBoost was developed as the primary prediction model and compared with SVM and Cox regression. Model performance was assessed using a held-out test set and decision curve analysis.
RESULTS
Among 4,418 patients, 594 (13.4%) sustained a secondary fragility fracture. Increased refracture risk was associated with older age, osteoporosis, low BMI, female sex, cardiovascular disease, visual impairment, syncope, non-standard rehabilitation, and postoperative Harris hip score < 80. In the test set, XGBoost achieved an AUC of 0.701 (95% CI, 0.657-0.743), with 61.8% sensitivity and 67.2% specificity at the default threshold. Decision curve analysis demonstrated the highest net benefit for XGBoost across threshold probabilities of approximately 7%-32%.
CONCLUSIONS
Secondary fragility fractures were associated with skeletal fragility, fall-related vulnerability, and impaired postoperative recovery. The interpretable XGBoost model showed moderate discrimination and potential clinical utility as an adjunctive screening tool to identify patients who may benefit from intensified secondary prevention. External validation and prospective evaluation are required before routine clinical implementation.
Shi-Zan He, Di Wu, Dajun Jiang et al.· International Orthopaedics· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
